Search

With, Sonography, celebrating its 10th birthday, it is timely to reflect on the changes in ultrasound and the role of the sonographer, across the same period. This paper will present the significant changes that have occurred across the last 10 years in a large public hospital network in Australia across a diversity of themes. In the areas where challenges have emerged, the way these were navigated will be described. Documenting this change in ultrasound provision may be valuable to future planning for all key stakeholders. [ABSTRACT FROM AUTHOR]

Purpose: Artificial intelligence (AI)‐based systems have demonstrated great potential in improving the diagnostic accuracy of retinal disease but are yet to achieve widespread acceptance in routine clinical practice. Clinician attitudes are known to influence implementation. Therefore, this study aimed to identify optometrists' attitudes towards the use of AI to assist in diagnosing retinal disease. Methods: A paper‐based survey was designed to assess general attitudes towards AI in diagnosing retinal disease and motivators/barriers for future use. Two clinical scenarios for using AI were evaluated: (1) at the point of care to obtain a diagnostic recommendation, versus (2) after the consultation to provide a second opinion. Relationships between participant characteristics and attitudes towards AI were explored. The survey was mailed to 252 randomly selected practising optometrists across Australia, with repeat mail‐outs to non‐respondents. Results: The response rate was 53% (133/252). Respondents' mean (SD) age was 42.7 (13.3) years, and 44.4% (59/133) identified as female, whilst 1.5% (2/133) identified as gender diverse. The mean number of years practising in primary eye care was 18.8 (13.2) years with 64.7% (86/133) working in an independently owned practice. On average, responding optometrists reported positive attitudes (mean score 4.0 out of 5, SD 0.8) towards using AI as a tool to aid the diagnosis of retinal disease, and would be more likely to use AI if it is proven to increase patient access to healthcare (mean score 4.4 out of 5, SD 0.6). Furthermore, optometrists expressed a statistically significant preference for using AI after the consultation to provide a second opinion rather than during the consultation, at the point‐of‐care (+0.12, p = 0.01). Conclusions: Optometrists have positive attitudes towards the future use of AI as an aid to diagnose retinal disease. Understanding clinician attitudes and preferences for using AI may help maximise its clinical potential and ensure its successful translation into practice. [ABSTRACT FROM AUTHOR]

Extensive riparian vegetation clearance occurred in many rivers of southeastern Australia throughout the 19th and 20th century, post colonisation. With improvements in river management practices, coincident with a period of minimal flooding, vegetation recovery of riparian corridors has been occurring since the 1980s in all coastal catchments of New South Wales (NSW). However, the catchment‐by‐catchment spatial pattern and temporal trends, trajectories and rates of vegetative recovery remain unknown. We reconstruct a 70‐year time series of change in riparian vegetation coverage for all rivers in coastal catchments of NSW, utilising historical aerial imagery, Landsat and Sentinel data and a manual digitisation and machine learning method. We quantify and statistically analyse decadal trends in woody and non‐woody vegetation coverage along 19 485 km of stream length in 20 catchments. Across the region, there has been, on average, a 40% increase in vegetation coverage along riparian corridors since the 1950s, with some catchments increasing towards a current day coverage of between 60% and 80%. However, the trends vary by subregion and by catchment. An early logarithmic increase occurred up to 2004 on the North coast, and a recent and accelerated exponential increase since 1995 has occurred on the South coast. After a steep initial increase, riparian corridor vegetation coverage has fluctuated on the Central coast since about 1995. We used these linear, exponential and logarithmic regressions to undertake preliminary forecasts of possible future timeframes of riparian vegetation change, based on several climate, management and natural disaster disturbance scenarios. If the current trend continues, riparian vegetation coverage can reach 70% across the region by 2055. However, if management practices change or catastrophic disturbance events such as fire and flood occur, increases in riparian vegetation coverage could be set back by up to 30 to 40 years. [ABSTRACT FROM AUTHOR]

Many rural areas experience population stagnation or decline from out‐migration with corresponding economic downturns. This is the case for the Northern Territory in Australia, a vast and sparsely populated jurisdiction. Its government has long sought to encourage stronger population growth but its population is young and highly transient, leading to high staff turn‐overs and challenges for industries and government to attract families and skilled workers. Place‐based factors such as job opportunities, access to essential services or environmental amenities influence satisfaction and migration decisions. The aim of this study was to understand why people might stay or move away through analysing responses to two open‐text questions on the best and worst aspect of living in the Northern Territory. Over 3500 valid responses were analysed using machine learning‐based unsupervised topic modelling which uncovered latent clusters. Forty‐four percent of positive aspects were clustered into lifestyle factors, while negative aspects clustered around high living costs and crime. Some aspects, such as the weather and distance to other places were discussed as both positive and negative aspects. Topics discussed by respondents could be directly related to their intention to leave the Northern Territory, and also to specific individual's demographic characteristics providing insights for policies focused on attracting and retaining population. The use of unsupervised text mining in population research is rare and this study verifies its use to deliver objective and nuanced results generated from a large qualitative data set. [ABSTRACT FROM AUTHOR]

Artificial Intelligence (AI) is the ability for computers to simulate human intelligence. In dermatology, there is substantial interest in using AI to identify skin lesions from images. Due to increasing research and interest in the use of AI, the Australasian College of Dermatologists has developed a position statement to inform its members of appropriate use of AI. This article presents the ACD Position Statement on the use of AI in dermatology, and provides explanatory information that was used to inform the development of this statement. [ABSTRACT FROM AUTHOR]

Summary: Landscape rehabilitation following mining is required to be resilient to disturbance impacts such as fire, drought and disease. As mining companies undergo the process of rehabilitation certification and mine closure, there are notable knowledge gaps on the ecological risks associated with mature rehabilitated landscapes, based largely on the assumption that rehabilitation is analogous to reference communities. However, the response to fire disturbance across a range of landscapes remains largely untested and in particular there is limited understanding of recovery traits of plant species that occur naturally or are commonly seeded into rehabilitation. In August 2018, a controlled fire was applied to 37 hectares of 12‐year‐old coal‐mine rehabilitation in central Queensland, Australia. We used a combination of (i) ground plot surveys and (ii) drone imagery to compare the vegetation response of burnt woody species to unburnt controls prior to, and for, two years following the fire. The survival of the most dominant shrub species found on the rehabilitation site was significantly impacted by the fire. Old Man Saltbush (Atriplex nummularia Lindl. subsp. nummularia) recorded significant post‐fire mortality, with ground surveys recording an average reduction of 89% of stems per hectare across the burnt site, while unburnt controls remained unchanged. The plot data analysis was supported with high spatial and temporal resolution drone imagery, classified using a Random Forest machine‐learning approach. Change analysis of these maps showed a significant decline of 82% in Old Man Saltbush plant density and 92% reduction in foliage cover following the fire. In addition, the mean canopy area of individual Old Man Saltbush shrubs reduced significantly from a pre‐fire mean of 11.3 to 4.8 m2 two years following the fire. A spatial proximity analysis showed that those individuals that survived the fire were located significantly closer to unburnt areas and bare spoil, indicating that discontinuous ground fuel loads can greatly improve the survivability of individuals. This study provides new evidence on the contested fire sensitivity of Old Man Salt bush and demonstrates the risk that future climate‐driven extreme events may have on the resilience of novel ecosystems. [ABSTRACT FROM AUTHOR]

Wildfires not only severely damage the natural environment and global ecological balance but also cause substantial losses to global forest resources and human lives and property. Unprecedented fire events such as Australia's bushfires have alerted us to the fact that wildfire prediction is a critical scientific problem for fire management. Therefore, robust, long‐lead models and dynamic predictions of wildfire are valuable for global fire prevention. However, despite decades of effort, the dynamic, effective, and accurate prediction of wildfire remains problematic. There is great uncertainty in predicting the future based on historical and existing spatiotemporal sequence data, but with advances in deep learning algorithms, solutions to prediction problems are being developed. Here, we present a dynamic prediction model of global burned area of wildfire employing a deep neural network (DNN) approach that produces effective wildfire forecasts based on historical time series predictors and satellite‐based burned area products. A hybrid DNN that combines long short‐term memory and a two‐dimensional convolutional neural network (CNN2D‐LSTM) was proposed, and CNN2D‐LSTM model candidates with four different architectures were designed and compared to construct the optimal architecture for fire prediction. The proposed model was also shown to outperform convolutional neural networks (CNNs) and the fully connected long short‐term memory (FcLSTM) approach using the refined index of agreement and evaluation metrics. We produced monthly global burned area spatiotemporal prediction maps and adequately reflected the seasonal peak in fire activity and highly fire‐prone areas. Our combined CNN2D‐LSTM approach can effectively predict the global burned area of wildfires 1 month in advance and can be generalized to provide seasonal estimates of global fire risk. [ABSTRACT FROM AUTHOR]

This study evaluates the ability of machine learning algorithms to classify tropical depressions (TDs) and tropical storms (TSs) in the western region of the southwest Pacific Ocean (SWPO). Decision rules are generated to predict the environment required for a depression to fully develop into a mature storm, and the most influential predictors in the classification decision are ranked. TD and TS are discriminated based on a maximum sustained wind speed threshold (≥17 ms−1). Various aerosol, thermodynamic, and dynamic parameters are extracted closest to the initiation point of each non‐developing and developing sample. The covariates associated with each labelled sample are used to train a decision tree and random forest model. Results using a testing dataset suggest the random forest approach more accurately distinguishes between non‐developing and developing samples. The classification accuracy of the decision tree and random forest are 72% and 91%, respectively. Random forest outperformed the decision tree by providing higher accuracy in test data. The most important variables for binary classification are sea salt aerosol optical depth (AOD), 1,000 mb relative humidity, and sea surface temperature. AOD is a quantitative estimate of the aerosols presents in the air through the extinction of a ray of light as it passes through the atmosphere. Mean composite maps constructed in an unsupervised manner have been created for the most important variables identified by the random forest classifier during TD and TS events to highlight the difference in geophysical and aerosol variables' climatology during the two different classifications. This work will advance the risk management strategies for northeastern Australia and other SWPO basin islands to control their tropical cyclone related losses through prioritizing forecasting variables that are the strongest predictors of the strengthening of tropical depressions into tropical cyclones. [ABSTRACT FROM AUTHOR]

Long‐term hydrological partitioning of catchments can be well described by the Budyko framework with a parameter (e.g., Fu's equations with parameter ω). The Budyko framework considers aridity index as the dominant control on hydrological partitioning, while the parameter represents integrated influences of catchment properties. Our understanding regarding the controls of catchment properties on the parameter is still limited. In this study, two machine learning methods, that is, boosted regression tree (BRT) and CUBIST, were used to model ω. Interpretable machine learning methods were adopted for better physical understanding including feature importance, accumulated local effects (ALE), and local interpretable model‐agnostic explanations. Among the 15 properties of 443 Australian catchments, analysis of feature importance showed that root zone storage capacity (SR), vapor pressure, vegetation coverage (M), precipitation depth, climate seasonality and asynchrony index (SAI), and water use efficiency (WUE) were the six primary control factors on ω. ALE showed that ω varied nonlinearly with all factors, and varied non‐monotonically with M, SAI, and WUE. LIME showed that the importance of the six dominant factors on ω varied between regions. CUBIST was further used to build regionally varying relationships between ω and the primary factors. Continental scale ω and evapotranspiration were further mapped across Australia based on the most robust BRT‐trained parameterization scheme with a resolution of 0.05°. Instead of using the machine learning method as a black box, we employed interpretability approaches to identify the controls. Our findings not only improved the capability of the Budyko method for hydrological partitioning across Australia, but also demonstrated that the controls of catchment properties on hydrological partitioning vary in different regions. Key Points: Machine learning and further interpretation methods were jointly used for better understanding of controls on hydrological partitioningSix climatic and vegetation variables were identified as dominant controls but had region‐specific relationships with Budyko parameterParameterization of the Budyko parameter using machine learning outperforms traditional methods for mapping surface evaporation [ABSTRACT FROM AUTHOR]

Herbivore foraging decisions are closely related to plant nutritional quality. For arboreal folivores with specialized diets, such as the vulnerable greater glider (Petauroides volans), the abundance of suitable forage trees can influence habitat suitability and species occurrence. The ability to model and map foliar nitrogen would therefore enhance our understanding of folivore habitat use at finer scales. We tested whether high‐resolution multispectral imagery, collected by a lightweight and low‐cost commercial unoccupied aerial vehicle (UAV), could be used to predict total and digestible foliar nitrogen (N and digN) at the tree canopy level and forest stand‐scale from leaf‐scale chemistry measurements across a gradient of mixed‐species Eucalyptus forests in southeastern Australia. We surveyed temperate Eucalyptus forests across an elevational and topographic gradient from sea level to high elevation (50–1200 m a.s.l.) for forest structure, leaf chemistry, and greater glider occurrence. Using measures of multispectral leaf reflectance and spectral indices, we estimated N and digN and mapped N and favorable feeding habitat using machine learning algorithms. Our surveys covered 17 Eucalyptus species ranging in foliar N from 0.63% to 1.92% dry matter (DM) and digN from 0.45% to 1.73% DM. Both multispectral leaf reflectance and spectral indices were strong predictors for N and digN in model cross‐validation. At the tree level, 79% of variability between observed and predicted measures of nitrogen was explained. A spatial supervised classification model correctly identified 80% of canopy pixels associated with high N concentrations (≥1% DM). We developed a successful method for estimating foliar nitrogen of a range of temperate Eucalyptus species using UAV multispectral imagery at the tree canopy level and stand scale. The ability to spatially quantify feeding habitat using UAV imagery allows remote assessments of greater glider habitat at a scale relevant to support ground surveys, management, and conservation for the vulnerable greater glider across southeastern Australia. [ABSTRACT FROM AUTHOR]